Question about training FSANET_Capsule

[xxxillllll]

It is fine when training SSRNET_MT, but when training FSANET_Capsule, an error comes.

Traceback (most recent call last):
  File "FSANET_train.py", line 299, in <module>
    main()
  File "FSANET_train.py", line 132, in main
    model = FSA_net_Capsule(image_size, num_classes, stage_num, lambda_d, S_set)()
  File "..\lib\FSANET_model.py", line 444, in __call__
    ssr_Cap_list = ssr_aggregation_model(ssr_primcaps)
  File "E:\Anaconda3\envs\bishe\lib\site-packages\keras\engine\topology.py", line 603, in __call__
    output = self.call(inputs, **kwargs)
  File "E:\Anaconda3\envs\bishe\lib\site-packages\keras\engine\topology.py", line 2061, in call
    output_tensors, _, _ = self.run_internal_graph(inputs, masks)
  File "E:\Anaconda3\envs\bishe\lib\site-packages\keras\engine\topology.py", line 2265, in run_internal_graph
    assert str(id(x)) in tensor_map, 'Could not compute output ' + str(x)
AssertionError: Could not compute output Tensor("reshape_8/Reshape:0", shape=(?, ?), dtype=float32)

And my environment is the same as the environment you list.
Thank you!

[PotentialPie]

It is fine when training SSRNET_MT, but when training FSANET_Capsule, an error comes.

Traceback (most recent call last):
  File "FSANET_train.py", line 299, in <module>
    main()
  File "FSANET_train.py", line 132, in main
    model = FSA_net_Capsule(image_size, num_classes, stage_num, lambda_d, S_set)()
  File "..\lib\FSANET_model.py", line 444, in __call__
    ssr_Cap_list = ssr_aggregation_model(ssr_primcaps)
  File "E:\Anaconda3\envs\bishe\lib\site-packages\keras\engine\topology.py", line 603, in __call__
    output = self.call(inputs, **kwargs)
  File "E:\Anaconda3\envs\bishe\lib\site-packages\keras\engine\topology.py", line 2061, in call
    output_tensors, _, _ = self.run_internal_graph(inputs, masks)
  File "E:\Anaconda3\envs\bishe\lib\site-packages\keras\engine\topology.py", line 2265, in run_internal_graph
    assert str(id(x)) in tensor_map, 'Could not compute output ' + str(x)
AssertionError: Could not compute output Tensor("reshape_8/Reshape:0", shape=(?, ?), dtype=float32)

And my environment is the same as the environment you list.
Thank you!

I have the same problem as you.
The environment is the same.

[xxxillllll]

It is fine when training SSRNET_MT, but when training FSANET_Capsule, an error comes.

Traceback (most recent call last):
  File "FSANET_train.py", line 299, in <module>
    main()
  File "FSANET_train.py", line 132, in main
    model = FSA_net_Capsule(image_size, num_classes, stage_num, lambda_d, S_set)()
  File "..\lib\FSANET_model.py", line 444, in __call__
    ssr_Cap_list = ssr_aggregation_model(ssr_primcaps)
  File "E:\Anaconda3\envs\bishe\lib\site-packages\keras\engine\topology.py", line 603, in __call__
    output = self.call(inputs, **kwargs)
  File "E:\Anaconda3\envs\bishe\lib\site-packages\keras\engine\topology.py", line 2061, in call
    output_tensors, _, _ = self.run_internal_graph(inputs, masks)
  File "E:\Anaconda3\envs\bishe\lib\site-packages\keras\engine\topology.py", line 2265, in run_internal_graph
    assert str(id(x)) in tensor_map, 'Could not compute output ' + str(x)
AssertionError: Could not compute output Tensor("reshape_8/Reshape:0", shape=(?, ?), dtype=float32)

And my environment is the same as the environment you list.
Thank you!

I have the same problem as you.
The environment is the same.

My solution is to use py3.6 and change keras,tf... correspondingly.
The environment the writer lists, is not suitable for the latest code.

[PotentialPie]

It is fine when training SSRNET_MT, but when training FSANET_Capsule, an error comes.

Traceback (most recent call last):
  File "FSANET_train.py", line 299, in <module>
    main()
  File "FSANET_train.py", line 132, in main
    model = FSA_net_Capsule(image_size, num_classes, stage_num, lambda_d, S_set)()
  File "..\lib\FSANET_model.py", line 444, in __call__
    ssr_Cap_list = ssr_aggregation_model(ssr_primcaps)
  File "E:\Anaconda3\envs\bishe\lib\site-packages\keras\engine\topology.py", line 603, in __call__
    output = self.call(inputs, **kwargs)
  File "E:\Anaconda3\envs\bishe\lib\site-packages\keras\engine\topology.py", line 2061, in call
    output_tensors, _, _ = self.run_internal_graph(inputs, masks)
  File "E:\Anaconda3\envs\bishe\lib\site-packages\keras\engine\topology.py", line 2265, in run_internal_graph
    assert str(id(x)) in tensor_map, 'Could not compute output ' + str(x)
AssertionError: Could not compute output Tensor("reshape_8/Reshape:0", shape=(?, ?), dtype=float32)

And my environment is the same as the environment you list.
Thank you!

I have the same problem as you.
The environment is the same.

My solution is to use py3.6 and change keras,tf... correspondingly.
The environment the writer lists, is not suitable for the latest code.

I just reinstalled the environment and everything went well....
There must be some problems but I haven't found.